Adam
Adam: A Method for Stochastic Optimization. We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
Keywords for this software
References in zbMATH (referenced in 400 articles )
Showing results 1 to 20 of 400.
Sorted by year (- Angeli, Andrea; Desmet, Wim; Naets, Frank: Deep learning for model order reduction of multibody systems to minimal coordinates (2021)
- Barakat, Anas; Bianchi, Pascal: Convergence and dynamical behavior of the ADAM algorithm for nonconvex stochastic optimization (2021)
- Benjamin Paaßen, Jessica McBroom, Bryn Jeffries, Irena Koprinska, Kalina Yacef: ast2vec: Utilizing Recursive Neural Encodings of Python Programs (2021) arXiv
- Bertsimas, Dimitris; Dunn, Jack; Wang, Yuchen: Near-optimal nonlinear regression trees (2021)
- Canchumuni, Smith W. A.; Castro, Jose D. B.; Potratz, Júlia; Emerick, Alexandre A.; Pacheco, Marco Aurélio C.: Recent developments combining ensemble smoother and deep generative networks for facies history matching (2021)
- Chi, Heng; Zhang, Yuyu; Tang, Tsz Ling Elaine; Mirabella, Lucia; Dalloro, Livio; Song, Le; Paulino, Glaucio H.: Universal machine learning for topology optimization (2021)
- David Salinas, Valentin Flunkert, Jan Gasthaus: DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks (2021) arXiv
- Eckstein, Stephan; Kupper, Michael: Computation of optimal transport and related hedging problems via penalization and neural networks (2021)
- Furelos-Blanco, Daniel; Law, Mark; Jonsson, Anders; Broda, Krysia; Russo, Alessandra: Induction and exploitation of subgoal automata for reinforcement learning (2021)
- Gao, Yu; Zhang, Kai: Machine learning based data retrieval for inverse scattering problems with incomplete data (2021)
- Gu, Shihao; Kelly, Bryan; Xiu, Dacheng: Autoencoder asset pricing models (2021)
- Haghighat, Ehsan; Raissi, Maziar; Moure, Adrian; Gomez, Hector; Juanes, Ruben: A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics (2021)
- Han, Seongji; Choi, Hee-Sun; Choi, Juhwan; Choi, Jin Hwan; Kim, Jin-Gyun: A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations (2021)
- Hao, Wenrui: A gradient descent method for solving a system of nonlinear equations (2021)
- He, Fang; Chun, Rachel Ka Man; Qiu, Zicheng; Yu, Shijie; Shi, Yun; To, Chi Ho; Chen, Xiaojun: Choroid segmentation of retinal OCT images based on CNN classifier and (l_2-l_q) fitter (2021)
- Hernandez, Quercus; Badías, Alberto; González, David; Chinesta, Francisco; Cueto, Elías: Deep learning of thermodynamics-aware reduced-order models from data (2021)
- Jiang, Su; Durlofsky, Louis J.: Data-space inversion using a recurrent autoencoder for time-series parameterization (2021)
- Kafka, Dominic; Wilke, Daniel N.: Resolving learning rates adaptively by locating stochastic non-negative associated gradient projection points using line searches (2021)
- Kalogeris, Ioannis; Papadopoulos, Vissarion: Diffusion maps-aided neural networks for the solution of parametrized PDEs (2021)
- Kharazmi, Ehsan; Zhang, Zhongqiang; Karniadakis, George E. M.: \textithp-VPINNs: variational physics-informed neural networks with domain decomposition (2021)